OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

etnaviv/nn: Fix use of etna_core_info

Browse Source 
Right now we were retrieving the properties of the NPU from the
etna_core_info of the GPU.

Fixes: 92a6f697d5 ("etnaviv: npu: Switch to use etna_core_info")
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
(cherry picked from commit f9bb9aa7d5)

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32119>
This commit is contained in:
Tomeu Vizoso
2024-11-06 10:26:20 +01:00
committed by Dylan Baker
parent e839ff344e
commit e86386df89
5 changed files with 29 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.pick_status.json
View File

@@ -504,7 +504,7 @@
"description": "etnaviv/nn: Fix use of etna_core_info",
"nominated": true,
"nomination_type": 2,
"resolution": 0,
"resolution": 1,
"main_sha": null,
"because_sha": "92a6f697d589c926edf712ca40a7742ce7d187d7",
"notes": null

11
src/gallium/drivers/etnaviv/etnaviv_ml.c
View File

@@ -61,6 +61,13 @@ etna_ml_create_tensor(struct etna_ml_subgraph *subgraph, unsigned idx, unsigned
ML_DBG("created resource %p for tensor %d with size %d\n", res, idx, size);
}
struct etna_core_npu_info *
etna_ml_get_core_info(struct etna_context *context) {
struct etna_screen *screen = context->screen;
struct etna_core_info *info = etna_gpu_get_core_info(screen->npu);
return &info->npu;
}
static bool
needs_reshuffle(const struct pipe_ml_operation *poperation)
{
@@ -237,7 +244,7 @@ etna_ml_subgraph_create(struct pipe_context *pcontext,
unsigned count)
{
struct etna_context *ctx = etna_context(pcontext);
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
struct etna_ml_subgraph *subgraph;
struct list_head operations;
unsigned tensor_count;
@@ -358,7 +365,7 @@ void
etna_ml_subgraph_invoke(struct pipe_context *pctx, struct pipe_ml_subgraph *psubgraph, struct pipe_tensor *input)
{
struct etna_context *ctx = etna_context(pctx);
unsigned tp_core_count = ctx->screen->info->npu.tp_core_count;
unsigned tp_core_count = etna_ml_get_core_info(ctx)->tp_core_count;
struct etna_ml_subgraph *subgraph = (struct etna_ml_subgraph *)(psubgraph);
struct etna_cmd_stream *stream = ctx->stream;
static bool is_initialized = false;

3
src/gallium/drivers/etnaviv/etnaviv_ml.h
View File

@@ -8,6 +8,7 @@
#include "pipe/p_state.h"
#include "util/u_dynarray.h"
#include "etnaviv_context.h"
#define MAX_CONFIG_BOS 4
@@ -94,6 +95,8 @@ unsigned etna_ml_allocate_tensor(struct etna_ml_subgraph *subgraph);
struct pipe_resource *etna_ml_get_tensor(struct etna_ml_subgraph *subgraph, unsigned idx);
unsigned etna_ml_get_offset(struct etna_ml_subgraph *subgraph, unsigned idx);
struct etna_core_npu_info *etna_ml_get_core_info(struct etna_context *context);
struct pipe_ml_subgraph *
etna_ml_subgraph_create(struct pipe_context *context,
const struct pipe_ml_operation *operations,

26
src/gallium/drivers/etnaviv/etnaviv_ml_nn.c
View File

@@ -515,8 +515,8 @@ etna_ml_lower_add(struct etna_ml_subgraph *subgraph,
static unsigned
calc_superblocks(struct etna_context *ctx, const struct etna_operation *operation, unsigned tile_y, unsigned interleave_mode)
{
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned nn_accum_buffer_depth = ctx->screen->info->npu.nn_accum_buffer_depth;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
unsigned nn_accum_buffer_depth = etna_ml_get_core_info(ctx)->nn_accum_buffer_depth;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
unsigned kernels_per_core = DIV_ROUND_UP(output_channels, nn_core_count);
unsigned foo = (nn_accum_buffer_depth * interleave_mode) / tile_y;
@@ -590,8 +590,8 @@ calc_addition_sizes(unsigned *input_width, unsigned *input_height, unsigned *inp
static unsigned
calculate_tiling(struct etna_context *ctx, const struct etna_operation *operation, unsigned *tile_width_out, unsigned *tile_height_out)
{
unsigned nn_input_buffer_depth = ctx->screen->info->npu.nn_input_buffer_depth;
unsigned nn_accum_buffer_depth = ctx->screen->info->npu.nn_accum_buffer_depth;
unsigned nn_input_buffer_depth = etna_ml_get_core_info(ctx)->nn_input_buffer_depth;
unsigned nn_accum_buffer_depth = etna_ml_get_core_info(ctx)->nn_accum_buffer_depth;
unsigned input_width = operation->input_width;
unsigned input_height = operation->input_height;
unsigned input_channels = operation->input_channels;
@@ -639,9 +639,9 @@ create_nn_config(struct etna_ml_subgraph *subgraph, const struct etna_operation
{
struct pipe_context *context = subgraph->base.context;
struct etna_context *ctx = etna_context(context);
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
unsigned nn_core_version = ctx->screen->specs.nn_core_version;
unsigned oc_sram_size = ctx->screen->info->npu.on_chip_sram_size;
unsigned oc_sram_size = etna_ml_get_core_info(ctx)->on_chip_sram_size;
struct etna_bo *bo = etna_bo_new(ctx->screen->dev,
sizeof(struct etna_nn_params),
DRM_ETNA_GEM_CACHE_WC);
@@ -967,7 +967,7 @@ static unsigned
write_core_6(struct etna_ml_subgraph *subgraph, uint32_t *map, unsigned core, const struct etna_operation *operation, unsigned zrl_bits)
{
struct pipe_context *pctx = subgraph->base.context;
unsigned nn_core_count = etna_context(pctx)->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(etna_context(pctx))->nn_core_count;
unsigned input_channels = operation->addition ? 1 : operation->input_channels;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
unsigned cores_used = MIN2(output_channels, nn_core_count);
@@ -1047,7 +1047,7 @@ static unsigned
write_core_interleaved(struct etna_ml_subgraph *subgraph, uint32_t *map, unsigned core, const struct etna_operation *operation, unsigned zrl_bits)
{
struct pipe_context *pctx = subgraph->base.context;
unsigned nn_core_count = etna_context(pctx)->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(etna_context(pctx))->nn_core_count;
unsigned input_channels = operation->addition ? 1 : operation->input_channels;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
unsigned cores_used = MIN2(output_channels, nn_core_count);
@@ -1134,7 +1134,7 @@ static unsigned
write_core_sequential(struct etna_ml_subgraph *subgraph, uint32_t *map, unsigned core, const struct etna_operation *operation, unsigned zrl_bits)
{
struct pipe_context *pctx = subgraph->base.context;
unsigned nn_core_count = etna_context(pctx)->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(etna_context(pctx))->nn_core_count;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
unsigned cores_used = MIN2(output_channels, nn_core_count);
unsigned kernels_per_core = DIV_ROUND_UP(output_channels, cores_used);
@@ -1221,7 +1221,7 @@ calculate_weight_bo_size(struct etna_ml_subgraph *subgraph, const struct etna_op
{
struct pipe_context *context = subgraph->base.context;
struct etna_context *ctx = etna_context(context);
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
unsigned header_size = ALIGN(nn_core_count * 4, 64);
unsigned input_channels = operation->addition ? 1 : operation->input_channels;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
@@ -1245,8 +1245,8 @@ calculate_zrl_bits(struct etna_ml_subgraph *subgraph, const struct etna_operatio
{
struct pipe_context *context = subgraph->base.context;
struct etna_context *ctx = etna_context(context);
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned max_zrl_bits = ctx->screen->info->npu.nn_zrl_bits;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
unsigned max_zrl_bits = etna_ml_get_core_info(ctx)->nn_zrl_bits;
unsigned header_size = ALIGN(nn_core_count * 4, 64);
unsigned input_channels = operation->addition ? 1 : operation->input_channels;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;
@@ -1298,7 +1298,7 @@ create_coefficients_bo(struct etna_ml_subgraph *subgraph, const struct etna_oper
{
struct pipe_context *context = subgraph->base.context;
struct etna_context *ctx = etna_context(context);
unsigned nn_core_count = ctx->screen->info->npu.nn_core_count;
unsigned nn_core_count = etna_ml_get_core_info(ctx)->nn_core_count;
unsigned header_size = ALIGN(nn_core_count * 4, 64);
unsigned input_channels = operation->addition ? 1 : operation->input_channels;
unsigned output_channels = operation->addition ? 1 : operation->output_channels;

6
src/gallium/drivers/etnaviv/etnaviv_ml_tp.c
View File

@@ -394,7 +394,7 @@ create_reshuffle_config(struct etna_ml_subgraph *subgraph, const struct etna_ope
unsigned tp_core, unsigned tp_cores_used)
{
struct etna_context *ctx = etna_context(subgraph->base.context);
unsigned tp_core_count = ctx->screen->info->npu.tp_core_count;
unsigned tp_core_count = etna_ml_get_core_info(ctx)->tp_core_count;
struct etna_bo *bo = etna_bo_new(ctx->screen->dev,
sizeof(struct etna_tp_params),
DRM_ETNA_GEM_CACHE_WC);
@@ -730,7 +730,7 @@ etna_ml_compile_operation_tp(struct etna_ml_subgraph *subgraph,
instruction->configs[0] = create_detranspose_config(subgraph, operation);
break;
case ETNA_ML_TP_RESHUFFLE: {
unsigned tp_core_count = ctx->screen->info->npu.tp_core_count;
unsigned tp_core_count = etna_ml_get_core_info(ctx)->tp_core_count;
unsigned tp_cores_used;
tp_cores_used = (operation->input_width > 8 || operation->input_channels > 1) ? tp_core_count : 1;
@@ -756,7 +756,7 @@ etna_ml_emit_operation_tp(struct etna_ml_subgraph *subgraph,
unsigned idx)
{
struct etna_context *ctx = etna_context(subgraph->base.context);
unsigned tp_core_count = ctx->screen->info->npu.tp_core_count;
unsigned tp_core_count = etna_ml_get_core_info(ctx)->tp_core_count;
struct etna_cmd_stream *stream = ctx->stream;
bool more_than_one_tp_job = operation->configs[1] != NULL;
bool parallel = DBG_ENABLED(ETNA_DBG_NPU_PARALLEL);